“Mengyuan Zhao 2016-02-22”版本间的差异
来自cslt Wiki
（以“# 7*2048 chain model trainning done, worse than nnet3 model. # Study nnet3 LSTM configuration in detail, and try to run chain training with modified LSTM structure.”为内容创建页面） |
（没有差异）
|
2016年2月22日 (一) 02:03的最后版本
- 7*2048 chain model trainning done, worse than nnet3 model.
- Study nnet3 LSTM configuration in detail, and try to run chain training with modified LSTM structure.
